diff --git a/examples/csmsc/tts2/README.md b/examples/csmsc/tts2/README.md
index 290c288d2..ecd8ff180 100644
--- a/examples/csmsc/tts2/README.md
+++ b/examples/csmsc/tts2/README.md
@@ -1,3 +1,4 @@
+
 # SpeedySpeech with CSMSC
 This example contains code used to train a [SpeedySpeech](http://arxiv.org/abs/2008.03802) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html). NOTE that we only implement the student part of the Speedyspeech model. The ground truth alignment used to train the model is extracted from the dataset using [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner).
 
@@ -116,12 +117,9 @@ pwg_baker_ckpt_0.4
 ```
 `./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`.
 ```bash
-`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. 
-
 CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
-
-`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
 ```
+`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
 ```text
 usage: synthesize.py [-h]
                      [--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech,tacotron2_aishell3}]
@@ -168,12 +166,9 @@ optional arguments:
 ```
 `./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file.
 ```bash
-`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. 
-
-CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
-
-`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
 ```text
 usage: synthesize_e2e.py [-h]
                          [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}]